Adding HDF5 format using wetb

pydatview/io/__init__.py

@@ -69,9 +69,14 @@ def fileFormats(userpath=None, ignoreErrors=False, verbose=False):
     from .raawmat_file            import RAAWMatFile
     from .rosco_discon_file       import ROSCODISCONFile
     from .rosco_performance_file  import ROSCOPerformanceFile
+    try:
+        from .hawc2_hdf5_file               import HAWC2Hdf5File
+    except ImportError:
+        HAWC2Hdf5File=None
     from .plot3d_file             import Plot3DFile
     from .yaml_file               import YAMLFile
     from .airfoil_file            import AirfoilShapeFile
+
     priorities = []
     formats = []
     def addFormat(priority, fmt):
@@ -97,6 +102,8 @@ def addFormat(priority, fmt):
     addFormat(30, FileFormat(HAWCStab2PwrFile))
     addFormat(30, FileFormat(HAWCStab2IndFile))
     addFormat(30, FileFormat(HAWCStab2CmbFile))
+    if HAWC2Hdf5File is not None:
+        addFormat(30, FileFormat(HAWC2Hdf5File))
     addFormat(30, FileFormat(MannBoxFile))
     addFormat(40, FileFormat(FLEXBladeFile))
     addFormat(40, FileFormat(FLEXProfileFile))

pydatview/io/hawc2_hdf5_file.py

@@ -0,0 +1,43 @@
+from .wetb.gtsdf.gtsdf import load
+from .file import File, WrongFormatError
+import numpy as np
+import pandas as pd
+
+class HAWC2Hdf5File(File):
+
+    @staticmethod
+    def defaultExtensions():
+        return ['.hdf5']
+
+    @staticmethod
+    def formatName():
+        return 'HAWC2 hdf5 file'
+
+    def __init__(self, filename=None, **kwargs):
+        self.info = {}
+        self.data = np.array([])
+        super(HAWC2Hdf5File, self).__init__(filename=filename, **kwargs)
+
+    def _read(self):
+        try:
+            time, data, info = load(self.filename)
+            self.time = time
+            self.time = self.time.reshape(self.time.size, 1) # force shape(C, 1) for concatenation
+            self.data = data
+            self.info['attribute_names'] = info['attribute_names']
+            self.info['attribute_units'] = info['attribute_units']
+            self.info['attribute_descr'] = info['attribute_descriptions']
+        except WrongFormatError as e:
+            raise WrongFormatError('hdf5 File {}: '.format(self.filename)+'\n'+e.args[0])
+
+    def _toDataFrame(self):
+        # Appending time to form the dataframe
+        names = ['Time'] + self.info['attribute_names']
+        units = ['s']    + self.info['attribute_units']
+        units = [u.replace('(','').replace(')','').replace('[','').replace(']','') for u in units]
+        data  = np.concatenate((self.time, self.data), axis=1)
+        cols = [n + '_[' + u + ']' for n, u in zip(names, units)]
+        return pd.DataFrame(data=data, columns=cols)
+
+    def _write(self):
+        pass             

pydatview/io/wetb/AUTHORS.rst

@@ -0,0 +1,7 @@
+==========
+Developers
+==========
+
+* Mads Mølgaard Pedersen
+* David R.S. Verelst
+* Carlo Tibaldi

pydatview/io/wetb/LICENSE.txt

@@ -0,0 +1,14 @@
+wetb is free software; you can redistribute it and/or modify it under the terms
+of the GNU General Public License (GPL, http://www.gnu.org/copyleft/gpl.html)
+as published by the Free Software Foundation; either version 3 of the License,
+or (at your option) any later version.
+
+wetb is distributed in the hope that it will be useful, but WITHOUT ANY
+WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A
+PARTICULAR PURPOSE.
+
+See the GNU General Public License for more details http://www.gnu.org/licenses/
+
+We encourage you to submit new code for possible inclusion in future versions of
+wetb.
+

pydatview/io/wetb/README.md

@@ -0,0 +1,6 @@
+
+The wind energy toolbox (WETB) is available here:
+
+https://toolbox.pages.windenergy.dtu.dk/WindEnergyToolbox/
+
+License and authors can be found in this directory.

pydatview/io/wetb/gtsdf/__init__.py

@@ -0,0 +1,74 @@
+"""
+The 'General Time Series Data Format', gtsdf, is a binary hdf5 data format for storing time series data,\n
+specified by \n
+Mads M. Pedersen (mmpe@dtu.dk), DTU-Wind Energy, Aeroelastic design (AED)
+
+Features:
+
+-    Single file
+-    Optional data type, e.g. 16bit integer (compact) or 64 bit floating point (high precision)
+-    Precise time representation (including absolute times)
+-    Additional data blocks can be appended continuously
+-    Optional specification of name and description of dataset
+-    Optional specification of name, unit and description of attributes
+-    NaN support
+
+This module contains three methods:
+
+- load_
+- save_
+- append_block_
+
+.. _load: gtsdf.html#gtsdf.load
+.. _save: gtsdf.html#gtsdf.save
+.. _append_block: gtsdf.html#gtsdf.append_block
+
+"""
+
+d = None
+d = dir()
+
+from .gtsdf import save
+from .gtsdf import load
+from .gtsdf import append_block
+from .gtsdf import load_pandas
+
+class Dataset(object):
+    def __init__(self, filename):
+        self.filename = filename
+        self.time, self.data, self.info = load(filename)
+    def __call__(self, id):
+        if isinstance(id, str):
+            if id=="Time":
+                return self.time
+            else:
+                return self(self.info['attribute_names'].index(id) + 2)
+        if id == 1:
+            return self.time
+        else:
+            return self.data[:, id - 2]
+
+    def attribute_names_str(self):
+        return "\n".join(["1: Time"]+["%d: %s"%(i,n) for i, n in enumerate(self.info['attribute_names'],2)])
+
+    def __getattribute__(self, name):
+        try:
+            return object.__getattribute__(self, name)
+
+        except Exception as e:
+            try:
+                return self(name)
+            except:
+#                 for i, n in enumerate(self.info['attribute_names']):
+#                     print (i,n)
+                raise e
+
+    def __contains__(self, name):
+        return name in self.info['attribute_names']
+
+
+__all__ = sorted([m for m in set(dir()) - set(d)])
+
+
+
+